JP2016189097A - Abnormal driving detection device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an abnormal driving detection device that can accurately detect abnormal driving of another movable body.SOLUTION: A control part 2 photographs another vehicle and its surroundings with cameras 3 to 6, specifies a reference object on the basis of a photographed image, measures the degree of driving on the basis of a change in relative position between the reference object and the another vehicle, and outputs reminder information indicating abnormal driving of the another vehicle on the basis of the degree of driving from a speaker 7 and a display part 8. The control part measures the degree of driving with the reference object as a reference so as to accurately detect abnormal driving of the another vehicle.SELECTED DRAWING: Figure 4

Description

  The present invention relates to an abnormal operation detection device that measures the driving degree of another moving body and outputs warning information.

  Conventionally, a driving support device (abnormal driving detection device) for detecting a wobbling of an object has been proposed with a bicycle or the like positioned in front of or on the side of the own vehicle (own moving body) as an object (another moving body). (For example, refer to Patent Document 1). In the conventional driving support device described in Patent Document 1, the number of times the fluctuation width of the object exceeds a predetermined value is measured, and a warning is issued to the driver so as to avoid contact with the object. It has become.

JP 2012-194863 A

  However, in the driving support device of Patent Document 1, since the host vehicle and the object are traveling in the same direction, the criterion for determining the wobbling width is not clear, and the detection accuracy of the abnormal operation of the object is low. There was an inconvenience.

  Therefore, an object of the present invention is to provide an abnormal operation detection device that can accurately detect abnormal operation of another moving body.

  In order to solve the above-described problem and achieve the object, the abnormal operation detection device according to the present invention according to claim 1 shoots the periphery of the other moving body including the other moving body located around the own moving body. An imaging unit, a measurement unit that specifies a reference object based on a captured image captured by the imaging unit, and measures a driving degree indicating a change in a relative position between the reference object and the other moving body, and the driving degree And an output unit for outputting alert information indicating abnormal operation of the other moving body.

  The abnormal operation detection method of the present invention according to claim 5 includes a photographing step of photographing the periphery of the other moving body including the other moving body located in the vicinity of the own moving body, and a photographed image photographed in the photographing step. Based on the above, a reference object is specified, and a measurement process for measuring a driving degree indicating a change in a relative position between the reference object and the other moving body, and a caution indicating an abnormal operation of the other moving body based on the driving degree. And an output process for outputting the arousal information.

It is a block diagram which shows the outline of the abnormal operation detection apparatus which concerns on the Example of this invention. It is a flowchart which shows an example of the procedure of the abnormality detection process which the said abnormal driving | running | working detection apparatus performs. It is a flowchart which shows an example of the procedure of the other vehicle detection process in the said abnormality detection process. It is a flowchart which shows an example of the procedure of the shake detection process in the said abnormality detection process. It is a flowchart which shows an example of the procedure of the speed change detection process in the said abnormality detection process. It is a flowchart which shows an example of the procedure of the measurement end determination process in the said abnormality detection process.

  Embodiments of the present invention will be described below. The abnormal operation detection device according to the embodiment of the present invention is based on an imaging unit that images the periphery of another moving body, including other moving bodies that are located around the moving body, and a captured image that is captured by the imaging unit. A measurement unit that identifies an object and measures a driving degree indicating a change in a relative position between the reference object and another moving body, and an output unit that outputs warning information indicating an abnormal driving of the other moving body based on the driving degree; .

  According to such an abnormal operation detection device of the present embodiment, the reference object is specified based on the captured image by the imaging unit, and the driving degree indicating the change in the relative position between the reference object and the other moving body is measured. The abnormal operation of the other moving body can be accurately detected with reference to the reference object. Note that the driving degree may include a plurality of parameters, and a reference value may be set independently for each parameter, or a reference value may be set so as to comprehensively determine the plurality of parameters. In addition, the output unit may output the alert information for the mobile body or may output the alert information for a mobile body around another mobile body.

  At least one of: self-moving body information indicating a state of the self-moving body; other moving body information indicating a state of the other moving body; and road information indicating a state of the road on which the moving body and the other moving body are traveling. An environment acquisition unit that acquires environmental information including one and a reference value acquisition unit that acquires a reference value based on the environmental information, and the output unit alerts the driver when the driving degree exceeds the reference value It is preferable to output information. As a result, in addition to measuring the driving degree of other moving objects, by acquiring a reference value based on environmental information, the standard is used when deviation from normal driving is likely to occur or the possibility of contact is low. When the value is increased and deviation is difficult to occur or when the possibility of contact is high, abnormal operation of other moving bodies can be appropriately detected by decreasing the reference value. The normal running means that the speed change is small and the left / right wobbling is small. Furthermore, environmental information shows the own mobile body information which shows the state of the own mobile body, the other mobile body information which shows the state of another mobile body, and the state of the road on which the mobile body and the other mobile body are traveling. By including at least one of the road information, the reference value for the driving degree can be appropriately set according to the state of the own mobile body, the other mobile body, and the road. In addition, it is more preferable that the self-moving body information includes the traveling speed of the self-moving body. In addition, the other mobile body information may include at least one of the traveling speed of the other mobile body and the sign information (for example, the initial driver sign or the old driver sign) attached to the other mobile body. preferable. More preferably, the road information includes at least one of a road surface state, a lane width, the presence / absence of an obstacle on the road, the curvature of the lane, and the number of continuous curves.

  The driving degree includes the width of the other moving body to the left and right, and the measurement unit identifies the installed object or the moving object provided along the road as the reference object, and the relative position between the reference object and the other moving object. It is preferable to measure the deflection width based on the above. Thereby, when the other moving body swings left and right, it can be determined that the operation is abnormal. In addition, when the measurement unit identifies an installation as a reference object, the swing width is accurately measured based on the relative position (that is, the interval) between the installation and the other moving body, and the other moving body has swung from side to side. Can be detected. On the other hand, when the measuring unit specifies the host vehicle as a reference object, it can be detected whether the other moving body has swung left and right, assuming that the own moving body is traveling without swinging left and right. When the other moving body is positioned before and after the own moving body and the own vehicle is used as a reference object, any part of the own moving body and the other moving body is used as the reference position, and the relative positions of the reference positions in the left-right direction are relative to each other. Based on the change in position, the swing width can be measured. In addition, when the other moving body is positioned on the left and right of the own moving body and the own vehicle is used as a reference object, the swing width is measured based on the relative position with respect to the other moving body (that is, the moving body interval in the left-right direction). can do. In addition, it is more preferable that the measurement unit specifies at least one of a white line that separates the lane, a guard rail, a sidewalk, and a wall portion provided at an end in the width direction of the road as an installation object (reference object). .

  The driving degree includes the speed change amount of the other moving body, and the measurement unit can identify the own moving body as a reference object and measure the speed change amount based on the relative position between the own moving body and the other moving body. preferable. As a result, when the other moving body is accelerated or decelerated, it can be determined that the operation is abnormal. Furthermore, the relative speed between the moving body and the other moving body can be calculated based on the change in relative position over time, and assuming that the moving body is traveling at a constant speed, the other moving body is accelerated or decelerated. Can be detected. When the other moving body is positioned before and after the own moving body, the relative speed can be calculated by calculating the time change of the relative position with respect to the other moving body (that is, the moving body interval). In addition, when the other moving body is located on the left and right of the own moving body, the time change of the relative position between the reference positions in the front-rear direction is calculated using the arbitrary position of the own moving body and the other moving body as the reference position. Thus, the relative speed can be calculated.

  Note that the photographing unit may photograph the periphery of another moving body that is located in at least one of the front, rear, left, and right sides of the moving body. Thereby, it is possible to easily avoid contact by detecting abnormal operation of another moving body located in an appropriate direction with respect to the own moving body.

  In addition, the abnormal operation detection method according to the embodiment of the present invention is based on a photographing process for photographing the periphery of another moving body, including other moving bodies positioned around the own moving body, and a photographed image photographed in the photographing process. , A reference process to identify the reference object, measure the driving degree indicating the change in the relative position of the reference object and the other moving object, and output warning information indicating abnormal operation of the other moving object based on the driving degree And a process. According to such an abnormal operation detection method of the present embodiment, similarly to the above-described abnormal operation detection device, the reference object is measured by measuring the driving degree indicating the change in the relative position between the reference object and the other moving body. As a reference, it is possible to accurately detect abnormal operation of other moving bodies.

  Moreover, it is good also as an abnormal operation detection program which performs the abnormal operation detection method mentioned above by computer. By doing so, it is possible to detect an abnormal operation of another moving body with high accuracy using a computer.

  Further, the abnormal operation detection program described above may be stored in a computer-readable recording medium. In this way, the program can be distributed as a single unit in addition to being incorporated in the device, and version upgrades can be easily performed.

  Examples of the present invention will be specifically described below. FIG. 1 is a block diagram illustrating an outline of an abnormal operation detection device 1 according to an embodiment of the present invention, and FIG. 2 is a flowchart illustrating an example of an abnormality detection process performed by the abnormal operation detection device 1. FIG. 3 is a flowchart showing an example of the procedure of the other vehicle detection process in the abnormality detection process, FIG. 4 is a flowchart showing an example of the procedure of the shake detection process in the abnormality detection process, and FIG. FIG. 6 is a flowchart illustrating an example of a procedure of a measurement end determination process in the abnormality detection process.

  The abnormal operation detection device 1 of the present embodiment is mounted on the own vehicle as the own moving body and detects an abnormal operation of the other vehicle as the other moving body. As shown in FIG. A front camera 3, a rear camera 4, a left camera 5, a right camera 6, a speaker 7, a display unit 8, and a vehicle communication unit 9.

  The control unit 2 is configured by a CPU (Central Processing Unit) having a memory such as a RAM (Random Access Memory) and a ROM (Read Only Memory), for example, and governs overall control of the abnormal operation detection device 1. The control unit 2 may be a control unit provided in an in-vehicle device such as a navigation device or a meter, or may be a control unit dedicated to the abnormal operation detection device 1 independently of the in-vehicle device. Further, as will be described later, the control unit 2 functions as a measurement unit by measuring the driving degree based on the captured images of the cameras 3 to 6 and acquires a reference value for the driving degree. It functions as a part.

  The cameras 3 to 6 are configured to shoot front, rear, left, and right, respectively, and shoot the other vehicle located in the vicinity of the host vehicle and the periphery of the other vehicle, and transmit the photographed image to the control unit 2. Function as. The control unit 2 is configured to identify the reference object based on the captured images transmitted from the cameras 3 to 6 and measure the driving degree indicating the change in the relative position of the relative position between the reference object and the other vehicle. Yes. Moreover, the cameras 3-6 are comprised so that the white line which extends along a road and divides a lane may also be image | photographed. When the white line (installed object) that extends along the road and divides the lane is specified as the reference object, the control unit 2 measures the change in the distance between the white line and the other vehicle in the left-right direction (width direction). When a vehicle is specified as a reference object, a vehicle interval in the front-rear direction (traveling direction) with another vehicle (front-rear vehicle) positioned forward and backward with respect to the host vehicle, and with another vehicle (left-right vehicle) positioned left and right Measure the vehicle spacing in the left-right direction and the change in relative position in the left-right direction with the front and rear vehicles. When measuring the change in the relative position in the left-right direction with respect to the front and rear vehicles, the center line of the host vehicle (substantially the center position in the left-right direction) is compared with the center line of the other vehicle.

  The speaker 7 is configured to output warning information into the own vehicle by voice and functions as an output unit. Note that the speaker 7 may be a speaker for music reproduction mounted on a vehicle, for example. The display unit 8 is configured by a display screen such as a navigation device, for example, and is configured to output ambient ventilation information as an image. Such a speaker 7 and the display part 8 function as an output part. The output unit only needs to output at least one of an image and sound.

  The vehicle communication unit 9 communicates with the vehicle meter to acquire the traveling speed of the host vehicle (own vehicle speed) and is connected to the steering wheel to acquire the steering angle (that is, the steering angle of the wheels of the host vehicle). Then, a signal is transmitted to the control unit 2. In the present embodiment, the own vehicle speed is set as own vehicle information (environment information) as own vehicle information, and the vehicle communication unit 9 functions as an environment acquisition unit.

  In the present embodiment, the driving degree indicating the degree from the normal running in the other vehicle includes the deflection width to the left and right of the other vehicle and the speed change amount of the other vehicle, and is a deflection reference that is a reference value for the deflection width. A value and an interval reference value that is a reference value for the speed change amount are respectively determined.

  Here, the procedure in which the control unit 2 executes the abnormality detection process shown in FIG. 2 will be described. When a predetermined time elapses after the vehicle starts running, the control unit 2 starts the abnormality detection process shown in FIG. In the abnormality detection process, the control unit 2 first executes another vehicle detection process (S1). As shown in FIG. 3, in the other vehicle detection process, the control unit 2 acquires the host vehicle speed by the vehicle communication unit 9 (S20), and whether or not the host vehicle speed is equal to or higher than a start threshold (for example, 20 km / h). Is determined (S21). If the host vehicle speed is less than the start threshold (N in S21), the control unit 2 ends the other vehicle detection process. On the other hand, when the own vehicle speed is equal to or higher than the start threshold (Y in S21), the control unit 2 causes the cameras 3 to 6 to photograph the surroundings of the own vehicle (photographing process), and as another vehicle based on the photographed image. A vehicle interval in the front-rear direction with respect to the preceding vehicle is measured (S22), and it is determined whether or not the measured vehicle interval is equal to or less than an interval threshold value (for example, 50 m) (S23). The interval threshold value may be a constant value or may vary based on the host vehicle speed. If no other vehicle is detected, the vehicle interval is set to infinity. When the measured vehicle interval is equal to or less than the interval threshold (Y in S23), the control unit 2 determines that there is a front vehicle to be detected (S24), and when the measured vehicle interval is greater than the interval threshold (S23). N), and proceeds to the next step without passing through S24.

  Next, the control part 2 measures the vehicle space | interval in the front-back direction with the back vehicle as another vehicle (S25), and determines whether the measured vehicle space | interval is below an interval threshold value (S26). This interval threshold value may be equal to or different from the interval threshold value in S23. When the measured vehicle interval is equal to or smaller than the interval threshold (Y in S26), the control unit 2 determines that there is a rear vehicle to be detected (S27), and when the measured vehicle interval is larger than the interval threshold (S26). N), the process proceeds to the next step without passing through S27.

  Next, the control unit 2 measures the vehicle interval in the left-right direction with respect to the left and right vehicles as other vehicles (S28), and determines whether or not the measured vehicle interval is equal to or less than the interval threshold value (S29). When the measured vehicle interval is equal to or less than the interval threshold (Y in S29), the control unit 2 determines that there are left and right vehicles to be detected (S30), ends the other vehicle detection process, and the measured vehicle interval is If it is larger than the interval threshold (N in S29), the other vehicle detection process is terminated without passing through S30. In addition, the process of S28-S30 should just be implemented about the direction where another vehicle can exist among right and left, for example, when the own vehicle is drive | working the leftmost lane, object for the right side is made into object. do it. Further, when the host vehicle is traveling in the center lane of the three lanes, the steps S28 to S30 are performed for both the left and right other vehicles. Further, the interval threshold for the left and right vehicles is set to a value different from the interval threshold for the front and rear vehicles (for example, the width of one lane). Further, instead of S28 and S29, the relative position in the front-rear direction of the host vehicle and the left and right vehicles is measured, and the presence or absence of another vehicle is determined by determining whether the host vehicle and the left and right vehicles are separated in the front-rear direction. May be.

  The control unit 2 returns to the abnormality detection process again and determines whether there is another vehicle to be detected (S2). When there is no other vehicle to be detected (N in S2), the control unit 2 ends the abnormality detection process. On the other hand, when there is another vehicle to be detected (Y in S2), the control unit 2 determines whether or not the abnormal operation detection device 1 is in an on state (that is, an operating state) (S3). When the abnormal operation detection device 1 is in the off state (N in S3), the control unit 2 ends the abnormality detection process. On the other hand, when the abnormal operation detection device 1 is in the on state (Y in S3), the control unit 2 determines whether there are front and rear vehicles to be detected (S4). When there are front and rear vehicles to be detected (Y in S4), the control unit 2 executes a shake detection process (S5). On the other hand, when there are no front and rear vehicles to be detected (N in S4), the control unit 2 proceeds to S11 described later.

  In the shake detection process, as shown in FIG. 4, the control unit 2 first monitors the running state of the target other vehicle for a predetermined time (for example, 10 s) (S40) and starts measuring the detection time. (S41). Next, the control unit 2 determines whether or not a white line is detected by the front and rear cameras 3 and 4 (S42). When a white line is detected (Y in S42), the control unit 2 identifies the white line as a reference object, and sets the distance between the white line and the other vehicle in the left-right direction as a shake parameter (S43). It is assumed that the shake parameter increases as this interval increases and decreases as it decreases. On the other hand, when the white line is not detected (N in S42), the control unit 2 identifies the host vehicle as a reference object, and uses the relative position in the left-right direction of the center line of the other vehicle with respect to the center line of the host vehicle as a shake parameter ( S44). It is assumed that the shake parameter increases when the center line of the other vehicle moves to the right side with respect to the center line of the host vehicle, and decreases when the center line moves to the left side. Moreover, the reference | standard for measuring a relative position is not limited to a center line, What is necessary is just to be set to the appropriate position of the vehicle.

  Next, the control unit 2 acquires an initial value of the shake parameter (S45), and determines whether the detection time being measured is within a first measurement time (for example, 30 s) (S46). When the detection time is within the first measurement time (Y in S46), the control unit 2 acquires the steering angle of the host vehicle (S47) and determines whether the host vehicle is swinging left and right (S48). . At this time, for example, when the steering angle repeats a large change in a short time, it may be determined that the host vehicle is swinging left and right. When the host vehicle is not swinging left and right (N in S48), the control unit 2 acquires the host vehicle speed (S49, environment acquisition step) and determines whether the host vehicle speed is equal to or higher than the start threshold ( S50). If the detection time exceeds the first measurement time (N in S46), if the host vehicle is swinging left and right (Y in S48), and if the host vehicle speed is less than the start threshold (N in S50), The control unit 2 ends the shake detection process.

  On the other hand, when the own vehicle speed is equal to or higher than the start threshold (Y in S50), the control unit 2 acquires the shake parameter at that time (S51, measurement process), and shakes based on the own vehicle speed as environment information. A reference value is determined (S52, reference value acquisition step). The shake reference value may be determined so that, for example, the shake reference value decreases as the host vehicle speed increases. Next, the control unit 2 determines whether or not the absolute value of the difference (shake difference value) obtained by subtracting the initial value from the shake parameter acquired in S51 is within a preset shake upper limit value (S53). . When the absolute value is larger than the shake upper limit value (N in S53), the control unit 2 ends the shake detection process. That is, when the target other vehicle changes lanes or the like, the absolute value of the swing difference value becomes larger than the swing upper limit value, and the other vehicle is excluded from the detection target.

  On the other hand, when the absolute value of the shake difference value is within the shake upper limit value (Y in S53), the control unit 2 determines whether or not the absolute value of the shake difference value is equal to or greater than the shake reference value (S54). When the absolute value of the shake difference value is less than the shake reference value (N in S54), the control unit 2 returns to S46 again. On the other hand, when the absolute value of the shake difference value is equal to or larger than the shake reference value (Y in S54), the control unit 2 has a negative product of the shake difference value measured last time and the shake difference value measured this time. It is determined whether or not there is (S55). That is, it is determined whether the direction in which the other vehicle has moved last time is different from the direction in which the other vehicle has moved this time. When the product is a negative value (Y in S55), the control unit 2 increments the counter value of the number of shakes by 1 (S56). On the other hand, when the product is a positive value or 0 (N in S55) ), Return to S46. Following S56, the controller 2 determines whether or not the number of shakes is equal to or greater than a predetermined number of shake determinations (S57). When the number of shakes is less than the number of shake determinations (N in S57), the control unit 2 returns to S46. On the other hand, when the number of shakes is equal to or greater than the number of shake determinations (Y in S57), the control unit 2 determines the left and right shakes of the target front and rear vehicles (S58) and ends the shake detection process.

  When the shake detection process ends, the control unit 2 returns to the abnormality detection process again, and determines whether or not the left and right shakes of the front and rear vehicles have been determined in the shake detection process (S6). When the shake is not fixed (N in S6), the control unit 2 executes a speed change detection process (S7).

  In the speed change detection process, as shown in FIG. 5, the control unit 2 first acquires an initial value of the own vehicle speed (S60), specifies the own vehicle as a reference object, and sets an initial value of the vehicle interval between the preceding and following vehicles. Obtain (S61). Next, the control unit 2 starts measuring the detection time (S62). The control unit 2 determines whether the detection time being measured is within the second measurement time (S63). The second measurement time may be equal to the first measurement time, or may be set to a different value. When the detection time is within the second measurement time (Y in S63), the control unit 2 acquires the host vehicle speed (S64, environment acquisition step) and determines whether the host vehicle speed is constant ( S65). At this time, if the host vehicle speed is within a predetermined error range with respect to the initial value, it may be determined that the host vehicle speed is constant. When the host vehicle speed is constant (Y in S65), the control unit 2 determines whether or not the host vehicle speed is equal to or higher than the start threshold (S66). When the detection time exceeds the second measurement time (N in S63), the own vehicle speed is not constant (N in S65), and the own vehicle speed is less than the start threshold (N in S66), the control unit 2 ends the speed change detection process.

  On the other hand, when the host vehicle speed is equal to or higher than the start threshold value (Y in S66), the control unit 2 acquires the vehicle interval between the host vehicle and the other vehicle at that time (S67, measurement process), and serves as environmental information. An interval reference value is determined based on the host vehicle speed (S68, reference value acquisition step). Note that the interval reference value may be determined so as to decrease as the host vehicle speed increases, for example. Next, the control unit 2 determines whether or not the vehicle interval is equal to or less than the interval threshold (S69). When the vehicle interval is larger than the interval threshold (N in S69), the control unit 2 ends the speed change detection process. That is, when the target other vehicle is sufficiently distant, the other vehicle is excluded from the detection target.

  On the other hand, when the vehicle interval is equal to or smaller than the interval threshold (Y in S69), the control unit 2 determines whether the absolute value of the difference (interval difference value) obtained by subtracting the initial value from the vehicle interval acquired in S67 is equal to or greater than the interval reference value. It is determined whether or not (S70). When the absolute value of the interval difference value is less than the interval reference value (N in S70), the control unit 2 returns to S63 again. On the other hand, when the absolute value of the interval difference value is equal to or larger than the interval reference value (Y in S70), the control unit 2 has a negative product of the product of the interval difference value measured last time and the interval difference value measured this time. It is determined whether or not there is (S71). That is, it is determined whether the host vehicle has repeatedly approached or separated from other vehicles. When the product is a negative value (Y in S71), the control unit 2 increases the counter value of the number of changes by 1 (S72), and when the product is a positive value or 0 (N in S71), Return to S63. Following S72, the control unit 2 determines whether or not the number of changes is equal to or greater than a predetermined number of change determinations (S73). When the number of changes is less than the number of change determinations (N in S73), the control unit 2 returns to S63. On the other hand, when the number of changes is equal to or greater than the number of change determinations (Y in S73), the control unit 2 determines the speed change of the target front and rear vehicles (S74) and ends the speed change detection process.

  In the speed change detection process, since the change in the vehicle interval with the other vehicle is measured after it is determined that the host vehicle speed is constant, the change in the vehicle interval means that the speed of the other vehicle changes. Is equivalent to Therefore, it is the process which detects the speed change of another vehicle by measuring a vehicle space | interval.

  When the speed change detection process is completed, the control unit 2 returns to the abnormality detection process again, and determines whether or not the speed change of the preceding and following vehicles is confirmed in the speed change detection process (S8). When the speed change of the front and rear vehicles is not fixed (N in S8), the control unit 2 proceeds to S10 described later. When the shake of the front and rear vehicles is fixed (Y in S6) and when the speed change is fixed (Y in S8), the control unit 2 causes the speaker 7 and the display unit 8 to output alert information. (S9, output step). Next, the control unit 2 determines whether there are front and rear vehicles that are detection targets and have not been subjected to the shake detection process and the speed change detection process (S10). When there are unprocessed front and rear vehicles, the control unit 2 returns to S5 again. On the other hand, when there are no unprocessed front and rear vehicles (N in S10), the control unit 2 determines whether there are left and right vehicles to be detected (S11). When there are left and right vehicles to be detected (Y in S11), the control unit 2 executes left and right vehicle shake detection processing (S12). On the other hand, when there are no left and right vehicles to be detected (N in S11), the control unit 2 proceeds to S16 described later.

  The left and right vehicle shake detection process is substantially the same process as the shake detection process of FIG. 4, and specifies the own vehicle as a reference object and uses a vehicle interval in the left and right direction between the own vehicle and another vehicle as a shake parameter. That is, steps S42 to S44 are omitted. Further, the values used for the determination in the left and right vehicle shake detection processing (measurement time, shake upper limit value, shake reference value, and shake determination frequency) may be the same as or different from the values used in the shake detection process of FIG. May be.

  When the left / right vehicle shake detection process is completed, the control unit 2 returns to the abnormality detection process again, and determines whether or not the left / right vehicle shake has been determined (S13). When the left and right vehicle shake is not fixed (N in S13), the control unit 2 proceeds to S15 described later. On the other hand, when the shake of the left and right vehicles is confirmed (Y in S13), the control unit 2 causes the speaker 7 and the display unit 8 to output alert information (S14, output process). Next, the control unit 2 determines whether there is a left and right vehicle that is a detection target and that has not been subjected to left and right vehicle shake detection processing (S15). When there is an unprocessed left and right vehicle, the control unit 2 returns to S12 again. On the other hand, when there is no unprocessed left and right vehicle (N in S15), the control unit 2 executes a measurement end determination process (S16).

  In the measurement end determination process, as shown in FIG. 6, the control unit 2 first acquires the host vehicle speed (S80), and determines whether the host vehicle speed is equal to or higher than the start threshold (S81). When the host vehicle speed is less than the start threshold value (N in S81), the control unit 2 stops all alerts as a measurement end state (S82), and ends the measurement end determination process. On the other hand, when the host vehicle speed is equal to or higher than the start threshold value (Y in S81), the control unit 2 measures the vehicle interval with the preceding vehicle (S83), and determines whether the measured vehicle interval is equal to or less than the interval threshold value. Determine (S84). When the measured vehicle interval is larger than the interval threshold (N in S84), the control unit 2 determines that there is no preceding vehicle to be detected, stops alerting the preceding vehicle (S85), and measures the measured vehicle interval. Is equal to or smaller than the interval threshold value (Y in S84), the process proceeds to the next step without passing through S85.

  Next, the control part 2 measures the vehicle space | interval with a back vehicle (S86), and determines whether the measured vehicle space | interval is below a space | interval threshold value (S87). When the measured vehicle interval is larger than the interval threshold (N in S87), the control unit 2 determines that there is no rear vehicle to be detected, stops alerting the rear vehicle (S88), and measures the measured vehicle interval. Is equal to or less than the interval threshold (Y in S87), the process proceeds to the next step without passing through S88.

  Next, the control part 2 measures the vehicle space | interval with a right-and-left vehicle (S89), and determines whether the measured vehicle space | interval is below a space | interval threshold value (S90). When the measured vehicle interval is larger than the interval threshold (N in S90), the control unit 2 determines that there is no left and right vehicles to be detected, stops the alerting for the left and right vehicles (S91), and ends the measurement determination process. When the measured vehicle interval is equal to or smaller than the interval threshold (Y in S90), the measurement end determination process is terminated without passing through S91.

  With the above configuration, the reference object is specified based on the images taken by the cameras 3 to 6, and the driving degree is measured based on the change in the relative position between the reference object and the other vehicle. The abnormal operation can be detected with high accuracy.

  In addition to measuring the swing width and speed change amount as the driving degree of other vehicles, the standard value for the swing width and speed change amount is determined based on the own vehicle speed as the environmental information, so that normal driving is performed. When the deviation from the vehicle is likely to occur or when the possibility of contact is low, the reference value is increased.When the deviation is difficult or the possibility of contact is high, the reference value is decreased. Abnormal operation can be detected appropriately.

  Furthermore, since the environmental information includes the own vehicle speed, the reference value for the driving degree can be appropriately set. That is, when the host vehicle speed is high, it is likely that the vehicle will come into contact with other vehicles more easily than when the host vehicle is at low speed, and the higher the host vehicle speed, the lower the shake reference value and the interval reference value. Can be detected appropriately.

  Furthermore, when the driving degree includes the left and right swing width and speed change amount of the other vehicle, abnormal driving can be detected when the other vehicle swings left and right or accelerates or decelerates.

  In addition, this invention is not limited to the said Example, The other deformation | transformation etc. which can achieve the objective of this invention are included in this invention.

  For example, in the above-described embodiment, the host vehicle speed that is host vehicle information is exemplified as the environment information for determining the reference value for the driving degree. However, the environment information is not limited to the host vehicle speed, Other vehicle information indicating the state (other moving body information) and road information indicating the state of the road on which the host vehicle and the other vehicle are traveling may be included, or one of them may be included. A plurality of appropriate ones may be combined. In addition, an appropriate environment acquisition unit may be provided in the abnormal operation detection device 1 according to the environment information to be acquired.

  The other vehicle information may be, for example, the traveling speed of the other vehicle or sign information attached to the other vehicle (for example, an initial driver sign or an elderly driver sign). When the traveling speed of other vehicles is high, or when an initial driver sign or an elderly driver sign is attached, it is considered that the vehicle is likely to come into contact, and the reference value may be set low. The road information may be, for example, the road surface state, the lane width, the presence / absence of an obstacle on the road, the curvature of the lane, and the continuous number of curves. When the road surface is wet or frozen, or when the lane width is narrow, it is considered that contact is likely to occur, and the reference value may be set low. Also, if there are obstacles on the road, the lane curvature is small, or if the curve is continuous, it is considered that left and right runout is likely to occur even if the vehicle is running normally. Set it high.

  In the above embodiment, as the driving degree, the lateral swing width of the front and rear vehicles, the speed change of the front and rear vehicles, and the lateral swing width of the left and right vehicles are measured. The change may be measured to detect abnormal driving of the left and right vehicles. In other words, the host vehicle is specified as a reference object, and an appropriate portion of the host vehicle and the left and right vehicles (for example, the front end portion of the vehicle, the driver's seat position, etc.) is used as the reference position, and the time variation of the relative position between the reference positions is determined. The relative speed with respect to the left and right vehicles may be measured by measuring. Further, the other vehicle to be detected may be at least one of the front vehicle, the rear vehicle, and the left and right vehicles. Furthermore, the driving degree to be measured may include at least one of a lateral swing width and a speed change amount.

  Moreover, in the said Example, although the white line which divides a lane was illustrated as an installation thing, the installation object should just be provided along the road, for example, a guardrail, a curb, etc. may be sufficient.

  Further, in the above embodiment, when the own vehicle is not swinging left and right, the other vehicle's swing width is measured, and when the own vehicle speed is constant, the speed change amount of the other vehicle is measured. The absolute swing width of the other vehicle may be calculated based on the relative swing width of the other vehicle with respect to the steering angle of the host vehicle. Further, the absolute speed of the other vehicle may be calculated based on the relative speed of the other vehicle with respect to the own vehicle and the own vehicle speed.

  Moreover, in the said Example, when abnormal driving | running | working of the other vehicle was detected, it was supposed that warning information was output in the own vehicle, but by communicating with the vehicle that runs around the other vehicle, It is good also as a structure which shares information. Moreover, the information about abnormal driving may be transmitted from the own vehicle to the server, and the information may be distributed from the server to a vehicle traveling around another vehicle in the abnormal driving state.

  In addition, the best configuration, method and the like for carrying out the present invention have been disclosed in the above description, but the present invention is not limited to this. That is, although the present invention has been particularly illustrated and described with respect to particular embodiments, it will be understood that the present invention is not limited in shape to the embodiments described above without departing from the scope and spirit of the invention. Various modifications can be made by those skilled in the art in terms of materials, quantity, and other detailed configurations. Therefore, the description limiting the shape, material, etc. disclosed above is an example for easy understanding of the present invention, and does not limit the present invention. The description by the name of the member which remove | excluded the limitation of one part or all of such is included in this invention.

1 Abnormal operation detection device 2 Control unit (measurement unit, reference value acquisition unit)
3 Front camera (shooting unit)
4 Rear camera (shooting unit)
5 Left camera (shooting unit)
6 Right camera (shooting unit)
7 Speaker (output unit)
8 Display section (output section)
9 Vehicle communication department (environment acquisition department)

Claims (7)

An imaging unit that captures the area around the other moving body, including other moving bodies located around the own moving body,
A measurement unit that identifies a reference object based on a captured image captured by the imaging unit and measures a driving degree indicating a change in relative position between the reference object and the other moving body;
And an output unit that outputs warning information indicating abnormal operation of the other moving body based on the driving degree. Self-moving body information indicating a state of the self-moving body, other moving body information indicating a state of the other moving body, road information indicating a state of a road on which the self-moving body and the other moving body are traveling, and , An environment acquisition unit that acquires environment information including at least one of
A reference value acquisition unit that acquires a reference value based on the environmental information, and
The abnormal operation detection device according to claim 1, wherein the output unit outputs the alert information when the driving degree is equal to or higher than the reference value. The driving degree includes a lateral swing width of the other moving body,
The measuring unit identifies an installation or a moving object provided along a road as the reference object, and measures the deflection width based on a relative position between the reference object and the other moving object. The abnormal operation detection device according to claim 1, wherein the abnormal operation detection device is provided. The driving degree includes a speed change amount of the other moving body,
The said measurement part specifies the said mobile body as the said reference | standard thing, and measures the said amount of speed changes based on the relative position of the said mobile body and the said other mobile body. The abnormal operation detection device according to any one of the above. A photographing step for photographing the periphery of the other moving body, including other moving bodies located around the own moving body,
A measurement step for identifying a reference object based on the photographed image photographed in the photographing step and measuring a driving degree indicating a change in relative position between the reference object and the other moving body,
And an output step of outputting alert information indicating abnormal operation of the other moving body based on the driving degree.   6. An abnormal operation detection program according to claim 5, wherein the abnormal operation detection method according to claim 5 is executed by a computer.   A computer-readable recording medium in which the abnormal operation detection program according to claim 6 is stored.

Images